Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 5701 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.6519. Min Range: -1.6519

Max Act: 1.6519. Min Act: -0.0000

Data Index: 1218285 (C4 (Web Text))

Max Activating Token Index: 441

Text #1

Max Range: 1.6519. Min Range: -1.6519

Max Act: 1.1513. Min Act: -0.0000

Data Index: 810362 (C4 (Web Text))

Max Activating Token Index: 526

Text #2

Max Range: 1.6519. Min Range: -1.6519

Max Act: 1.1199. Min Act: -0.0000

Data Index: 427898 (C4 (Web Text))

Max Activating Token Index: 950

Text #3

Max Range: 1.6519. Min Range: -1.6519

Max Act: 0.9086. Min Act: -0.0000

Data Index: 277576 (C4 (Web Text))

Max Activating Token Index: 530

Text #4

Max Range: 1.6519. Min Range: -1.6519

Max Act: 0.8302. Min Act: -0.0000

Data Index: 1212862 (C4 (Web Text))

Max Activating Token Index: 956

Text #5

Max Range: 1.6519. Min Range: -1.6519

Max Act: 0.8421. Min Act: -0.0000

Data Index: 704653 (C4 (Web Text))

Max Activating Token Index: 379

Text #6

Max Range: 1.6519. Min Range: -1.6519

Max Act: 0.8218. Min Act: -0.0000

Data Index: 1124131 (C4 (Web Text))

Max Activating Token Index: 1001

Text #7

Max Range: 1.6519. Min Range: -1.6519

Max Act: 0.7729. Min Act: -0.0000

Data Index: 956244 (C4 (Web Text))

Max Activating Token Index: 884

Text #8

Max Range: 1.6519. Min Range: -1.6519

Max Act: 0.7174. Min Act: -0.0000

Data Index: 884330 (C4 (Web Text))

Max Activating Token Index: 660

Text #9

Max Range: 1.6519. Min Range: -1.6519

Max Act: 0.7078. Min Act: -0.0000

Data Index: 949810 (C4 (Web Text))

Max Activating Token Index: 115

Text #10

Max Range: 1.6519. Min Range: -1.6519

Max Act: 0.6792. Min Act: -0.0000

Data Index: 163382 (C4 (Web Text))

Max Activating Token Index: 90

Text #11

Max Range: 1.6519. Min Range: -1.6519

Max Act: 0.6746. Min Act: -0.0000

Data Index: 401933 (C4 (Web Text))

Max Activating Token Index: 490

Text #12

Max Range: 1.6519. Min Range: -1.6519

Max Act: 0.6856. Min Act: -0.0000

Data Index: 405071 (C4 (Web Text))

Max Activating Token Index: 158

Text #13

Max Range: 1.6519. Min Range: -1.6519

Max Act: 0.7032. Min Act: -0.0000

Data Index: 184119 (C4 (Web Text))

Max Activating Token Index: 730

Text #14

Max Range: 1.6519. Min Range: -1.6519

Max Act: 0.6758. Min Act: -0.0000

Data Index: 1242281 (C4 (Web Text))

Max Activating Token Index: 592

Text #15

Max Range: 1.6519. Min Range: -1.6519

Max Act: 0.6715. Min Act: -0.0000

Data Index: 414788 (C4 (Web Text))

Max Activating Token Index: 395

Text #16

Max Range: 1.6519. Min Range: -1.6519

Max Act: 0.6571. Min Act: -0.0000

Data Index: 411631 (C4 (Web Text))

Max Activating Token Index: 972

Text #17

Max Range: 1.6519. Min Range: -1.6519

Max Act: 0.6525. Min Act: 0.0000

Data Index: 941225 (C4 (Web Text))

Max Activating Token Index: 884

Text #18

Max Range: 1.6519. Min Range: -1.6519

Max Act: 0.6353. Min Act: -0.0000

Data Index: 130270 (C4 (Web Text))

Max Activating Token Index: 423

Text #19

Max Range: 1.6519. Min Range: -1.6519

Max Act: 0.5867. Min Act: -0.0000

Data Index: 44138 (C4 (Web Text))

Max Activating Token Index: 60